© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4356
    Prev
    Next
    INDEX
    Explanations

    instances of encouragement to maintain a state ("stay safe", "stay productive")

    oai_token-act-pair · gemini-2.0-flash

    words related to safety or staying secure

    np_token-act-pair-logits · gpt-4o-mini

    stay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -0.74
     Theſe
    -0.74
     endregion
    -0.71
     ſeveral
    -0.71
     Diſ
    -0.70
    RetentionPolicy
    -0.69
    MLLoader
    -0.67
     fevere
    -0.63
     Efq
    -0.63
    testens
    -0.61
    POSITIVE LOGITS
     المعيارى
    0.52
     initComponents
    0.51
     safe
    0.50
     Safe
    0.48
    LError
    0.47
    Safe
    0.47
    setVerticalGroup
    0.46
    enumi
    0.46
    laj
    0.46
    letzt
    0.46
    Activations Density 0.402%

    No Known Activations